Youngo Park (left) and Kwangpyo Choi, from Samsung Research’s Visual Technology team

It’s official: We’ve entered the era of 8K TVs. Around the world, sales of 8K displays are steadily increasing, and with TV manufacturers constantly adding more offerings to the mix, the 8K market is expected to continue to grow.

There are, however, a few challenges that need to be addressed before viewers around the world will be able to enjoy 8K’s stunning visuals in their entirety. First, more 8K content will need to be produced, and second, network connections need to be made capable of supporting the seamless streaming of 8K movies and shows.

To address these issues, researchers from Samsung Research, an advanced R&D hub within Samsung Electronics’ SET Business, have developed an AI Codec known as AI ScaleNet. First introduced at SDC19, this innovation enables the delivery of 8K content on networks that typically support only 4K speeds – without the need for additional infrastructure.

To learn more about AI ScaleNet’s development process and potential applications, Samsung Newsroom interviewed Kwangpyo Choi and Youngo Park – researchers from Samsung Research’s Visual Technology team, and the first individuals to suggest and develop this type of innovative technology.

Supporting More 8K Content

AI ScaleNet utilizes deep learning technology to minimize data loss during compression and enable 8K content to be streamed on networks with lower bandwidth capabilities.

Here’s how it works, in a nutshell: 8K content is compressed to 4K quality using an AI downscaler and transmitted to the user’s TV, which utilizes AI to upscale the content back to 8K quality. When asked to describe the inspiration for the technology, Choi specified a need for a new video compression and transmission technology in order to accommodate the ever-evolving media landscape, and to address related technical challenges.

“Multimedia content is rapidly moving online, so figuring out how to overcome bandwidth limitations for UHD content transmission has become a major task,” said Choi.

“With AI ScaleNet, users will be able to enjoy 8K-quality content, even at lower bandwidths,” added Park. “In fact, during periods of high network traffic, when speeds tend to drop, viewers can still expect content to be presented at a relatively higher quality.”

AI ScaleNet addresses bandwidth limitations within modern network infrastructures with what’s known as an adaptive AI Codec. “AI Adaptive Bit Rate Streaming refers to AI technology that adapts to various bandwidths and adjusts the resolution to enable seamless streaming,” said Choi.

The difference the technology makes is especially clear when using over-the-top (OTT) services, where viewers typically notice changes in picture quality. As Choi explained, however, Samsung’s AI Codec and AI ScaleNet technology utilize AI that adapts to changes in bandwidth and optimizes quality, so users enjoy the highest-quality streaming experience possible.

A Groundbreaking Innovation

As the researchers described, the development process wasn’t without its difficulties. “The most difficult part was ensuring compatibility with existing codec compression technologies,” said Choi. “How to design an easy-to-use algorithm that would be compatible with existing technologies, while delivering the intended performance at the same time was the question.”

Choi also noted difficulties that derived from gaps in perspective between the research and development teams. There were several considerations related to complexity, design and structure which researchers took for granted, and were questioned by the developers.

“We were able to achieve this result thanks to the synergy of both our team members, who worked closely to achieve the same goal, and colleagues who were focused on the technology’s commercialization,” said Park. “I believe that AI ScaleNet is the first technology to overcome bandwidth limitations by addressing complexity issues and separating the server and client sides, respectively. It’s relatively difficult to commercialize AI technology today for the purpose of enhancing resolution, which is different from commercializing AI for recognition and classification.”

Empowering Richer User Experiences with AI Technology

When asked how AI technology will contribute to the advancement of TV technologies in general, the researchers pointed to two possible directions.

“The first would be greater user convenience, and the second would be enhanced picture quality,” Choi began. “The first point is already being delivered with Bixby. To enhance people’s viewing experiences, technologies that support the best possible picture quality at minimum bandwidth, such as AI ScaleNet, should be continuously researched and developed.”

As the researchers noted, Samsung has big plans for this versatile technology. “AI ScaleNet has shown us that by overcoming challenges, we can help usher in the future and enrich the user experience,” said Park. “Going forward, we will continue to research and develop additional functionalities that add to users’ convenience, and through cooperation with content service providers, we hope to empower diverse services for Samsung devices.”

Samsung R&D Institute Poland at IWSLT 2019

2019 marks the third year in a row that Samsung R&D Institute Poland, in partnership with the U.K.’s University of Edinburgh (UEDIN), has received accolades at the International Workshop on Spoken Language Translation (IWSLT), one of the top two global workshops on automatic language translation, along with the Workshop on Machine Translation (WMT). This year, Samsung R&D Institute Poland won first place in two categories, the first being text-to-text translation from English to Czech and the second – an end-to-end system translating English speech into German text.

For the text-to-text translation category, researchers worked to develop a model to translate the transcript of a spoken English-language TED Talk into Czech. Developing their winning model required the Samsung team to develop large, filtered corpora from which to work and generate as much synthetic data as possible. The work done by the Samsung R&D Institute Poland team, together with additional modeling help from UEDIN, was selected as the best in the challenge by human evaluators. This means that the translations produced by Samsung R&D Institute Poland’s system scored the highest both in fluency and adequacy.

Samsung R&D Institute Poland’s participation in their second winning category this year, the end-to-end translation system from English to German, was a first for the team. The task was to produce a German-language transcription of an English-language TED Talk audio recording. This task required the development of a single model that could take an audio file input and subsequently produce a translated transcription. It was made more difficult by the deficiency of the provided audio sources, compared to typical speech recognition task. Samsung R&D Institute Poland proposed several innovative methods for end-to-end speech translation that mitigated this source paucity, obtaining a state-of-the-art result with their final system that won them first place in the challenge.

Samsung Research America at ICCV 2019

This October, researchers from Samsung Research America’s AI Center received first place in the International Conference on Computer Vision (ICCV)’s challenge: Linguistic Meets Image and Video Retrieval (Fashion IQ). ICCV is a premier international computer vision conference that took place in Seoul, Korea, this year.

The challenge Samsung Research America AI Center took part in, sponsored by IBM research, aims to develop conversational shopping assistants that are more natural and real-world applicable. The task given to Samsung Research America AI Center‘s team, the ‘Superraptors’, belonged to the domain of image retrieval. In the task, an input query was specified in the form of a candidate image as well as in two natural language expressions that describe the visual differences of the search target. The goal of this challenge was to gather opinions and experience from researchers on the emerging space of visual content retrieval with a natural language interface.

Samsung Research America AI Center’s submission to the challenge, “Multimodal Ensemble of Diverse Models for Image Retrieval Using Natural Language Feedback”, blended the given data in different modalities with multiple deep learning models. The team’s win marks the first time a Samsung Research team has won a multimodal (language and vision) challenge; previously, Samsung AI Center Moscow, Samsung R&D Institute Poland and Samsung R&D Institute China-Beijing have received awards in single modality challenges.